ClawHub
Back to skill

Security audit

Obsidian Cli

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Obsidian CLI reference skill with disclosed vault and plugin-development commands, but users should be careful with write and eval commands.

Install this only if you want Codex to operate on your Obsidian vault through the Obsidian CLI. Prefer explicit vault and file/path targets before writes, review commands that create or append content, and treat JavaScript eval or developer commands as plugin-debugging tools rather than general note-management commands.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is broadly phrased enough to trigger on generic note-taking, search, and development requests, increasing the chance the agent invokes a powerful vault-writing and app-control tool when the user did not specifically ask for Obsidian CLI actions. Because the skill also exposes plugin reload, JavaScript evaluation, DOM inspection, and file modification capabilities, overbroad routing expands the blast radius of accidental or unsafe tool use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation normalizes create, append, property:set, and other state-changing commands without warning that they modify vault contents, potentially overwrite data, or act on the active file by default. In an agent setting, missing safety guidance can lead to unintended writes, destructive edits, or changes to the wrong note or vault, especially when defaults are implicit.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.